Security audit
Security checks for vulnerabilities and agentic risk
This is a plain Markdown workflow skill for bug triage and development planning, with no code execution, persistence, credential handling, or hidden behavior.
This skill is reasonable to install if you want a general triage and planning checklist. Because its trigger language is broad, use judgment before applying it to security-sensitive, credential-related, infrastructure, or production-changing work, and review any commands or changes the agent proposes before execution.
The skill description is broadly framed for 'development work' and lacks narrow activation boundaries, making it easy for an agent to invoke this skill in many unrelated engineering contexts. Over-broad routing can bypass more specialized or safer skills, causing the agent to apply a generic workflow where tighter guardrails, domain-specific checks, or security review would be more appropriate.
The body of the skill presents a generic reusable workflow without clear scope limits or activation constraints, so an orchestrating agent may over-apply it to diverse tasks beyond bug triage. In security terms, this expands the skill's effective authority and increases the chance of unsafe task selection, incomplete risk handling, or omission of specialized review steps for sensitive development actions.
No suspicious patterns detected.
